Press "Enter" to skip to content

Jaded statisticians ban p-values from hypothesis testing

The InsideHigherEd write-up is here. The ASA statement is here:

“It’s science’s dirtiest secret: The ‘scientific method’ of testing hypotheses by statistical analysis stands on a flimsy foundation.” A November, 2013, article in Phys.org Science News Wire (2013) cited “numerous deep flaws” in null hypothesis significance testing. A ScienceNews article (Siegfried, 2014) on February 7, 2014, said “statistical techniques for testing hypotheses…have more flaws than Facebook’s privacy policies.”

Ouch. No word yet on whether or not the administration will call out the cops to remove the GTFF’s “save the p-value” banner from outside Johnson Hall.

5 Comments

  1. Anonymous 03/15/2016

    The p-value is fine. Those that abuse it are the problem.

  2. uomatters Post author | 03/15/2016

    And their name is legion.

  3. Thom Aquinas 03/16/2016

    Actually they didn’t mind the p-value as much, as long as it is provided with more context, in particular effect size and variance.

  4. M 03/16/2016

    All hail the sagacious Queen McCloskey!

Leave a Reply

Your email address will not be published. Required fields are marked *